You are here

Home » Content

Artificial Intelligence in Adaptive Control Strategy Design

Journal Name:

  • International Journal of Science and Engineering Investigations

Publication Year:

  • 2017

Key Words:

Author Name
Abstract (2. Language): 
Intelligent systems and their theoretical background in artificial intelligence have noticed enormous improvement these years. Their implementation in everyday life is real challenge for the scientists. One of the most present actions in our day–to–day living is use of traffic and transportation. Therefore there are challenges for the researchers to optimize traffic operations. The aim of this paper is to prove the ability of machine learning control technique known as reinforcement learning to respond to variable real-time traffic conditions and adapt while controlling freeway entry access. Learning agents have been implemented as controllers in order to provide optimal performance on the freeway corridor. The algorithm used was Q-learning algorithm. The effectiveness of the agents were measured by several measures: total travel time spend by all the vehicles in the network, delay of the all vehicles in the network, stop time. The results are promising, proving that the Q-learning algorithm is capable for optimal coordinated control of freeway entrance ramps.
Bookmark/Search this post with
FULL TEXT (PDF): 
PDF icon arastirmax-artificial-intelligence-adaptive-control-strategy-design.pdf
  • 4
112
115
  • English

REFERENCES

References: 

[1] Papageorgiou, M., “Automatic Control Methods in Traffic and Transportation”, Operations Research and Decision Aid Methodologies in Traffic and Transportation Management, NATO ASI Series, Springer, 1991.
[2] Kotsialos, A., Papageorgiou, M., Mangeas, M., Haj-Salem, H., “Coordinated and Integrated Control of Freeway Networks via Non-linear Optimal Control”, Transportation Research Part C, Vol. 10, Elsevier Science Ltd, Great Britain, 2002, pp. 65-84.
[3] Alessandri, A., Febbraro, A.D., and Ferrara, A., “A Two-Level Approach for the Control of Freeways”, Applications of Advanced Technologies in Transportation Engineering - Proceedings of the 4th International Conference, Capri, Italy, 1995, pp. 429-433.
[4] H.M. Zhang and S.G. Ritchie, “Freeway Ramp Metering Using Artificial Neural Networks”, Transportation Research Part C, Vol. 5, No. 5, Elsevier Science Ltd, Great Britain, 1997, pp. 273-286.
[5] K. Bogenberger, et al., “Design of a Genetic Fuzzy Approach for Ramp Metering”, IEEE Intelligent Transportation Systems, USA, 2000.
[6] X. Wang, et al., “Reinforcement Learning On‐Ramp Metering with or without Complete Information”, ASCE, 2010.
[7] N. Nilsson, “The Quest for Artificial Intelligence: A History of Ideas and Achievements”, Cambridge University Press, Cambridge, UK, 2010.
[8] P. Stone, et al., “One Hundred Year Study on Artificial Intelligence (AI100)”, Stanford University, 2016.
[9] D. Roozemond, and P.V.D. Veer, “Usability of Intelligent Agent Systems in Urban Traffic Control”, Delft University of Technology, Delft, The Netherlands, 1999.
[10] P. Katwijk, et al., “Test Bed for Multiagent Control Systems in Road Traffic Management”, Transportation Research Record, No. 1910, Washington, D.C., 2005.
[11] W. Genders, et al. “Using a Deep Reinforcement Learning Agent for Traffic Signal Control”, Cornell University Library, arXiv: 1611.01142, 2016.
[12] J.D. Carvel, and others, “Freeway Management Handbook, Texas Transportation”, U.S. Department of Transportation, FHWA, 1997.
[13] W.S. Homburger, et al, “Fundamentals of Traffic Engineering, Institute of Transportation Studies”, University of California, Berkeley, 1996.
[14] R.S. Sutton, and A.G. Barto, “Reinforcement Learning -An Introduction”, MIT Press, Cambridge, Massachusetts, 1998.
[15] T. Mitchell, “Machine learning”, McGraw-Hill, New York, USA, 1997.
[16] K. Veljanovska, “Development of an Optimal Adaptive Control Strategy for Motorway Access Control” (PhD Dissertation), Faculty of Technical Sciences, Sv. K. Ohridski University, Bitola, 2008.

Thank you for copying data from http://www.arastirmax.com